The 50-year-old science problem that has now been solved could allow for dramatic changes in the fight against infectious diseases, researchers say
Scientists have been trying to solve the 50-year-old problem of “protein folding”, which maps the 3D shapes of the proteins that are responsible for many diseases such as cancer and COVID-19.
Google’s Deepmind claims to have created a program called “AlphaFold”, which is an artificial intelligence that is able to solve those problems in just a matter of days.
According to experts, if it works, this solution would come “decades” before it was expected, and could potentially have transformative effects in the way that infectious diseases are treated.
There are 200 million proteins that are known of currently, but only a fraction of them have actually been unfolded for scientists to fully understand how they work and what they do.
It is currently “too early to say” if another nationwide COVID-19 lockdown will need to occur after Christmas, according to a senior cabinet minister. George Eustice has said that “you can’t rule anything out” when he was asked about further “stay at home” measures.
DeepMind had been working on this AI project with the 14th Community Wide Experiment on the Critical Assessment of Techniques for Protein Structure Prediction (CASP14), which is a group of scientists who have been looking into such matters since 1994.
“Proteins are extremely complicated molecules, and their precise three-dimensional structure is key to the many roles they perform, for example the insulin that regulates sugar levels in our blood and the antibodies that help us fight infections,” Dr John Moult, chair of CASP14, said.
“Even tiny rearrangements of these vital molecules can have catastrophic effects on our health, so one of the most efficient ways to understand disease and find new treatments is to study the proteins involved.”
“There are tens of thousands of human proteins and many billions in other species, including bacteria and viruses, but working out the shape of just one requires expensive equipment and can take years.”
Nobel Laureate and president of the Royal Society, Professor Venki Ramakrishnan, said: “This computational work represents a stunning advance on the protein-folding problem, a 50-year-old grand challenge in biology.”
“It has occurred decades before many people in the field would have predicted.”
This comes after Doctors, scientists and the hospitality industry all say that Boris Johnson’s plans for a Christmas bubble is a mistake; for five days between the dates of the 23rd and the 27th of December, people throughout the UK will be able to mix with other families in a Christmas bubble.
“It will be exciting to see the many ways in which it will fundamentally change biological research.”
DeepMind noted that among other things, the prediction of these protein structures could be an important part of responding to any future pandemics, and that it had already used its machine learning technology on the protein structures on SARS-CoV-2 coronavirus, which causes COVID-19.